Abstract
A pursuit problem is a multi-agents' benchmark problem, where four hunters pursue and capture the prey in a cell environment. We have proposed a staged view that reflects a human's view where we can see an object easily in the neighborhood but more difficult in the longer distance and easily in the center direction but more difficult in the righter and lefter directions. With the staged view, the information that hunters can obtain becomes unclear depending on distance and direction. By several simulations, we showed that hunters can capture the prey even with the staged view in the cell environment. In this paper, we propose a staged view in the real number environment, which is similar to the real world. Since the border of adjacent view stage is not clear in the real number environment unlike the cell environment. We formulate a gradually changing view on distance and direction by fuzzy sets. We apply fuzzy Q-Learning to the pursuit problem with the staged view. A result shows that hunters can learn effectively with the staged view in the real number environment and capture the prey.
